ai-safety-foundation / sparse_autoencoderLinks
Sparse Autoencoder for Mechanistic Interpretability
☆257Updated last year
Alternatives and similar repositories for sparse_autoencoder
Users that are interested in sparse_autoencoder are comparing it to the libraries listed below
Sorting:
- Using sparse coding to find distributed representations used by neural networks.☆261Updated last year
- ☆324Updated 3 weeks ago
- ☆234Updated 10 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- Sparsify transformers with SAEs and transcoders☆598Updated this week
- ☆109Updated 3 weeks ago
- Mechanistic Interpretability Visualizations using React☆272Updated 7 months ago
- ☆124Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆202Updated this week
- Training Sparse Autoencoders on Language Models☆900Updated this week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆622Updated last week
- ☆183Updated 3 weeks ago
- ☆157Updated 8 months ago
- ☆505Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆120Updated 5 months ago
- ☆51Updated 8 months ago
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- ☆121Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆512Updated last year
- This repository collects all relevant resources about interpretability in LLMs☆366Updated 9 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆786Updated this week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- ☆81Updated 5 months ago
- Modified to support crosscoder training.☆21Updated last week
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆292Updated 2 weeks ago
- ☆70Updated 2 months ago
- Sparse probing paper full code.☆58Updated last year
- ☆103Updated 5 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆141Updated this week